How to Browse Models in Model Catalog on DigitalOcean Gradient™ AI Inference Hub

Model Catalog in Inference Hub provides a list of all available foundation models and allows you to filter and review model attributes before deployment. You can use it to compare pricing, capabilities, and supported features to determine which model fits your use case.

To view the Model Catalog, go to the DigitalOcean Control Panel, and then in the left menu, click Inference Hub.

Browse the Model Catalog

From the Inference Hub page, click the Model Catalog tab to see all available commercial and DigitalOcean-hosted foundation models. The catalog displays the following information for each model:

• Name: The model name, provider, and model ID used for API requests.
• Type: The model classification, such as text, multimodal, image generation, and embedding.
• Capabilities: Supported features such as reasoning, agentic tasks & tool use, coding, chat, and more.
• Price: Input and output token pricing.

Click the Name, Type, Capabilities, or Price column headers to sort the catalog in ascending or descending order.

Filter Model Catalog

To filter the model catalog by certain attributes, in the top-right, click Filters, and then click the attributes you want to filter the catalog by. You can filter the following:

• Availability: How the model can be deployed, such as Serverless or Dedicated.
• Provider: The organization that develops or hosts the model, such as OpenAI, Meta, DeepSeek, Anthropic, Alibaba, or Mistral AI.
• Type: The model classification, such as Reasoning, Chat, Image, or Embedding.

If you want to find a specific model, at the top of the Model Catalog list, use the search bar to locate it by name or model ID.

Click a model to open its model card. For a full list of supported models, see our models page.

View Model Card

Each model card includes a Model Details tab with information about the model and an API Usage tab with endpoint and usage guidance to help you evaluate suitability for your workload.

To test the model, on the top-right of the model card, click Launch Playground to test and compare models using the Model Playground.

View Model Details

Under the Model Details tab includes:

• Description of the model, including its intended use cases and key characteristics.
• Type: Model classification such as text, multimodal, text & vision reasoning, image generation, embedding.
• Content Length: Maximum supported context window or input token limit.
• Parameters: Approximate number of model parameters, indicating model size if available.
• Input Cost: Price per input token. See the pricing page for more information.
• Output Cost: Price per output token generated by the model. See the pricing page for more information.
• Input Capabilities: Supported input modalities, such as text, documents, image, audio, video. Output Capabilities: Types of outputs the model can generate, such as text, image, video, audio, embeddings.

Use this information to compare models based on cost, feature support, and deployment options.

Under the Availability section, see how you can deploy the model:

• Serverless Inference: To use the model with serverless inference, on the right, click Create key, and then follow set up serverless inference to authenticate and send requests to the model.
• Dedicated Inference: To deploy the model with dedicated inference, on the right, click Deploy endpoint, and then follow set up dedicated inference to configure and deploy the endpoint.

View API Usage

The API Usage tab includes:

• CHAT COMPLETIONS: Shows how to send chat-style prompts to the model using the /v1/chat/completions endpoint. This section includes required parameters such as model, messages, temperature, and max_completion_tokens, along with example requests.

For complete request examples and parameter details, see Send Prompt to a Model Using the Chat Completions API.

Retrieve Model Data via the API

You can retrieve model data programmatically using the DigitalOcean API.

Use the following endpoints:

• To list all available models and their core attributes, use the /v2/gen-ai/models/catalog endpoint.

  This endpoint returns model name, model’s catalog id, classification, provider, context window, pricing, and other summary attributes. Results are returned regardless of user-specific access permissions.

• To retrieve detailed information for a specific model, provide the catalog id, and then use the /v2/genai/models/catalog/{id} endpoint.

  This endpoint returns the full model card, including description, supported modalities, capabilities, performance information, deployment support, and pricing.

These endpoints allow you to integrate model discovery into automation workflows, internal tooling, or evaluation pipelines.